© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107085
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgment towards individuals for their contributions or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eteria
    -0.06
    andler
    -0.06
    iral
    -0.06
    º
    -0.06
     Grass
    -0.06
     Grip
    -0.06
    ÑĤеÑĢи
    -0.06
    civil
    -0.06
     asm
    -0.06
    oday
    -0.06
    POSITIVE LOGITS
     hosp
    0.07
    alc
    0.07
    LEGRO
    0.07
    /lg
    0.07
    Ưá»
    0.07
    UART
    0.06
    (ic
    0.06
    iana
    0.06
    Versions
    0.06
     hon
    0.06
    Activations Density 0.002%

    No Known Activations